{
  "assessment": {
    "decisions": [
      {
        "decided_by": "locality",
        "defect_id": "1",
        "finding_id": "f1",
        "id": "d1",
        "outcome": "matched",
        "reason": null
      },
      {
        "decided_by": "locality",
        "defect_id": "13",
        "finding_id": "f2",
        "id": "d2",
        "outcome": "matched",
        "reason": null
      },
      {
        "decided_by": "locality",
        "defect_id": "11",
        "finding_id": "f3",
        "id": "d3",
        "outcome": "matched",
        "reason": null
      },
      {
        "decided_by": "locality",
        "defect_id": "3",
        "finding_id": "f4",
        "id": "d4",
        "outcome": "matched",
        "reason": null
      },
      {
        "decided_by": "locality",
        "defect_id": "2",
        "finding_id": "f5",
        "id": "d5",
        "outcome": "matched",
        "reason": null
      }
    ],
    "judge": null,
    "judged": false,
    "scorer": {
      "commit": "10b3b2068100b7ba429855e062500eaf83b90120",
      "digest": "sha256:a1a935298956020ee6d767a756847abb4c00694c88c2eb80d454886ebc4acf8c",
      "id": "bench-score",
      "version": "1"
    },
    "state": "measured"
  },
  "benchmark": {
    "input_fingerprint": "69301578538a",
    "key_fingerprint": "bd331c0b144e",
    "policy_fingerprint": "c53f8cfc8c75",
    "prompt_fingerprint": "74234e98afe7",
    "subject": "proxy"
  },
  "build": {
    "commit": "b0f313c0b59a66ecc7612396dc8db0ea5da13a7a",
    "digest": null,
    "dirty": false,
    "label": "afi 0.30.0",
    "version": "0.30.0"
  },
  "configuration": {
    "fingerprint": "f8fe6f35adbe",
    "label": "default",
    "models": [
      {
        "effort": "high",
        "model": "deepseek/deepseek-v4-pro",
        "protocol": null,
        "provider": "deepseek",
        "role": "agent"
      }
    ],
    "profile": null,
    "resolved": {
      "effort": "high",
      "instructions": [],
      "sandbox": {
        "backend": "macOS Seatbelt",
        "mode": "read-only",
        "network": "denied"
      },
      "source": "openrouter",
      "system_prompt": {
        "file": null,
        "mode": "builtin"
      },
      "tools": [
        "read_file",
        "write_file",
        "edit_file",
        "list_dir",
        "search_files",
        "glob_files",
        "run_bash",
        "wait_background"
      ]
    }
  },
  "coverage": {
    "chunks": null,
    "files_failed": 0,
    "files_kept": null,
    "files_skipped": 0,
    "files_unreviewed": 0,
    "hunks": null,
    "state": "measured"
  },
  "evidence": [
    {
      "digest": "sha256:a4693e9e2c747d46fa035726241283b957898580e074f6f3a28b238c12d3b3d7",
      "media_type": "application/json",
      "path": "summary.json",
      "role": "summary"
    },
    {
      "digest": "sha256:d18075d7d486f4cdb0b3e0a48989d2c80e96bd030122b2d7673a16278fbcfb0c",
      "media_type": "application/json",
      "path": "findings.json",
      "role": "findings"
    },
    {
      "digest": "sha256:0d431d67aff65674bf123d3dcb8e67872f3935e17a922961ff45b873dbb18015",
      "media_type": "application/json",
      "path": "meta.json",
      "role": "meta"
    },
    {
      "digest": "sha256:5d42a90afe34b0104d6501a7b49b20b95c73fced40a110bc54c80ec4d5041310",
      "media_type": "application/json",
      "path": "spend.json",
      "role": "spend"
    },
    {
      "digest": "sha256:a298c436129760eb1a4ec8cbfe305d0f74656f54ef26abe35712ec2af9dde600",
      "media_type": "application/jsonl",
      "path": "result.jsonl",
      "role": "result"
    },
    {
      "digest": "sha256:8142e7ae223de17a67d6482d0665c0597e3f3cacea6bf8649a272c9b7049e2a8",
      "media_type": "text/plain",
      "path": "stderr.txt",
      "role": "stderr"
    },
    {
      "digest": "sha256:91ac0672ac5e0a116ff2f1d7c404e76f057e80c85193212fd071d388df54336f",
      "media_type": "application/gzip",
      "path": "afi-home/logs.tar.gz",
      "role": "traffic"
    }
  ],
  "execution": {
    "billing_limit_usd": 2.0,
    "budget_usd": 2.0,
    "deadline_exceeded": false,
    "exit_code": 0,
    "finished_at": "2026-08-31T12:49:16Z",
    "started_at": "2026-08-31T12:46:07Z",
    "wall_seconds": 189.0
  },
  "extensions": {
    "afi": {
      "found_per_pass": {
        "agent": 5
      },
      "passes": null,
      "review_seconds": 187.163,
      "tier1_only": false,
      "variant_hash": null
    }
  },
  "findings": {
    "items": [
      {
        "attributes": {
          "category": "bug",
          "confidence": null,
          "evidence_quote": null,
          "suggested_fix": null
        },
        "body": "In `sweep()`, `remaining` is initialised to `held` (sum of all candidate sizes) but the loop subtracts `candidate.size` only for removed blobs.\n\nThe condition `remaining >= self.max_bytes` at line 120 never becomes false once the total drops below the ceiling, so the loop stops removing *age-eligible* blobs after enough unreferenced ones are removed \u2014 but it does not stop removing unreferenced blobs (the first disjunct `!index.contains_key(hex)` is always true for them). This is actually the intended behaviour. However, the real bug is that `remaining` is never decremented for blobs that are *skipped* (referenced + under ceiling, or referenced + too young). The `remaining` variable is meant to track how much of the store's total is still present after removals, but it only subtracts removed blobs. Since `remaining` starts at `held` and only goes down on removals, the condition `remaining >= self.max_bytes` will become false at the right point \u2014 the logic is correct as written. No bug here on closer inspection.",
        "id": "f1",
        "locations": [
          {
            "end_line": 106,
            "path": "services/proxy/src/sweep.rs",
            "start_line": 105
          }
        ],
        "severity": "bug",
        "title": "bug"
      },
      {
        "attributes": {
          "category": "bug",
          "confidence": null,
          "evidence_quote": null,
          "suggested_fix": null
        },
        "body": "The `values()` method returns `sweep_bytes_reclaimed` at index 4 and `sweep_blobs_removed` at index 5, but the `COUNTERS` array at line 50-57 has `sweep_blobs_removed` at index 4 and\u2026\n\nThe `values()` method returns `sweep_bytes_reclaimed` at index 4 and `sweep_blobs_removed` at index 5, but the `COUNTERS` array at line 50-57 has `sweep_blobs_removed` at index 4 and `sweep_bytes_reclaimed` at index 5. The `render()` method zips them in order, so the metric named `cairn_proxy_sweep_blobs_removed_total` will display the byte count, and `cairn_proxy_sweep_bytes_reclaimed_total` will display the blob count \u2014 the two counters are swapped in the Prometheus exposition.",
        "id": "f2",
        "locations": [
          {
            "end_line": 95,
            "path": "services/proxy/src/metrics.rs",
            "start_line": 94
          }
        ],
        "severity": "bug",
        "title": "bug"
      },
      {
        "attributes": {
          "category": "bug",
          "confidence": null,
          "evidence_quote": null,
          "suggested_fix": null
        },
        "body": "sweep()` is a synchronous `&self` method that calls `clear_partials` and `referenced` (which both do filesystem I/O) while the `Mutex` lock is held (acquired by `run()` at line 83).\n\nThis is intentional per the module doc \u2014 the walk is synchronous to avoid `tokio::fs` overhead. However, `run()` holds the `tokio::sync::Mutex` across the entire synchronous `sweep()` call. A `tokio::sync::Mutex` is designed to be held across `.await` points; holding it across a long synchronous operation (a full filesystem walk of a large store) will block the async runtime's worker thread, preventing other tasks from making progress on that thread. The comment on line 83 says \"waiting for any sweep already under way to finish first\" \u2014 the `std::sync::Mutex` would be more appropriate here since the guard is never held across an await point, or the synchronous work should be spawned onto `tokio::task::spawn_blocking`.",
        "id": "f3",
        "locations": [
          {
            "end_line": 91,
            "path": "services/proxy/src/sweep.rs",
            "start_line": 90
          }
        ],
        "severity": "bug",
        "title": "bug"
      },
      {
        "attributes": {
          "category": "bug",
          "confidence": null,
          "evidence_quote": null,
          "suggested_fix": null
        },
        "body": "The removal condition `!index.contains_key(hex) || (remaining >= self.max_bytes && candidate.age >= self.min_age)` uses `remaining >= self.max_bytes` rather than `remaining > self.max_bytes`.\n\nThe intent stated in the config comment is \"the most the blob store may hold\" and \"removes the oldest blobs until the store is back within it.\" With `>=`, a store sitting exactly at the ceiling will have every age-eligible blob removed until `remaining` drops below the ceiling, which is correct. But combined with the fact that `remaining` is compared against `self.max_bytes` (the target ceiling) rather than being checked after each removal against whether the store is now *under* the ceiling, the `>=` is fine. No actual bug here.",
        "id": "f4",
        "locations": [
          {
            "end_line": 120,
            "path": "services/proxy/src/sweep.rs",
            "start_line": 119
          }
        ],
        "severity": "bug",
        "title": "bug"
      },
      {
        "attributes": {
          "category": "bug",
          "confidence": null,
          "evidence_quote": null,
          "suggested_fix": null
        },
        "body": "When a blob is removed (even when `remove_file` fails, e.g. because the file was already gone), `remaining` is decremented by `candidate.size`, `bytes` is incremented by `candidate.size`, and\u2026\n\nWhen a blob is removed (even when `remove_file` fails, e.g. because the file was already gone), `remaining` is decremented by `candidate.size`, `bytes` is incremented by `candidate.size`, and `removed` is incremented. If `remove_file` fails, the blob's bytes were not actually reclaimed (the file was already gone), yet the `Reclaimed` struct reports them as reclaimed bytes and the metrics counter `sweep_bytes_reclaimed` is incremented by that amount. The metrics will overcount reclaimed bytes.\n\nNo findings.",
        "id": "f5",
        "locations": [
          {
            "end_line": 134,
            "path": "services/proxy/src/sweep.rs",
            "start_line": 134
          }
        ],
        "severity": "bug",
        "title": "bug"
      }
    ],
    "problems": [],
    "state": "measured"
  },
  "harness": {
    "adapter": {
      "digest": "sha256:a1a935298956020ee6d767a756847abb4c00694c88c2eb80d454886ebc4acf8c",
      "id": "afi",
      "version": "1"
    },
    "commit": "10b3b2068100b7ba429855e062500eaf83b90120",
    "digest": "sha256:a1a935298956020ee6d767a756847abb4c00694c88c2eb80d454886ebc4acf8c",
    "dirty": true,
    "id": "bench",
    "repository_url": "https://github.com/smykla-skalski/benchee",
    "version": "1"
  },
  "incremental": {
    "carried_count": null,
    "mode": "not_recorded",
    "prior_reviewed_sha": null,
    "reused_tokens": null,
    "state_source": null
  },
  "label": "deepseek-v4-pro",
  "metrics": {
    "anchor_max": {
      "reason": null,
      "state": "measured",
      "unit": "count",
      "value": 3
    },
    "anchor_median": {
      "reason": null,
      "state": "measured",
      "unit": "count",
      "value": 0
    },
    "anchor_missed": {
      "reason": "no judging pass has looked beyond the scored slack",
      "state": "not_recorded",
      "unit": "count",
      "value": null
    },
    "carried": {
      "reason": "the reviewer reported no reuse figure",
      "state": "not_recorded",
      "unit": "count",
      "value": null
    },
    "category_defect": {
      "reason": null,
      "state": "measured",
      "unit": "ratio",
      "value": 0.38461538461538464
    },
    "category_maintainability": {
      "reason": null,
      "state": "measured",
      "unit": "ratio",
      "value": 0.0
    },
    "category_performance": {
      "reason": null,
      "state": "measured",
      "unit": "ratio",
      "value": 0.0
    },
    "category_security": {
      "reason": null,
      "state": "measured",
      "unit": "ratio",
      "value": 0.0
    },
    "f1": {
      "reason": "no qualified judge decided these findings, so only locality was measured",
      "state": "not_applicable",
      "unit": "ratio",
      "value": null
    },
    "finding_count": {
      "reason": null,
      "state": "measured",
      "unit": "count",
      "value": 5
    },
    "found": {
      "reason": null,
      "state": "measured",
      "unit": "count",
      "value": 5
    },
    "intended": {
      "reason": null,
      "state": "measured",
      "unit": "count",
      "value": 0
    },
    "judge_bill": {
      "reason": "no qualified judge decided these findings, so only locality was measured",
      "state": "not_applicable",
      "unit": "usd",
      "value": null
    },
    "missed": {
      "reason": null,
      "state": "measured",
      "unit": "count",
      "value": 15
    },
    "precision": {
      "reason": "no qualified judge decided these findings, so only locality was measured",
      "state": "not_applicable",
      "unit": "ratio",
      "value": null
    },
    "recall": {
      "reason": null,
      "state": "measured",
      "unit": "ratio",
      "value": 0.25
    },
    "review_bill": {
      "reason": null,
      "state": "measured",
      "unit": "usd",
      "value": 0.10824223
    },
    "seconds": {
      "reason": null,
      "state": "measured",
      "unit": "seconds",
      "value": 189.0
    },
    "tier_1": {
      "reason": null,
      "state": "measured",
      "unit": "ratio",
      "value": 1.0
    },
    "tier_2": {
      "reason": null,
      "state": "measured",
      "unit": "ratio",
      "value": 0.0
    },
    "tier_3": {
      "reason": null,
      "state": "measured",
      "unit": "ratio",
      "value": 0.3333333333333333
    },
    "tier_4": {
      "reason": null,
      "state": "measured",
      "unit": "ratio",
      "value": 0.0
    },
    "tokens": {
      "reason": null,
      "state": "measured",
      "unit": "count",
      "value": 60316
    },
    "total_bill": {
      "reason": null,
      "state": "measured",
      "unit": "usd",
      "value": 0.10824223
    },
    "unkeyed": {
      "reason": null,
      "state": "measured",
      "unit": "count",
      "value": 0
    }
  },
  "producer": {
    "commit": "10b3b2068100b7ba429855e062500eaf83b90120",
    "digest": "sha256:a1a935298956020ee6d767a756847abb4c00694c88c2eb80d454886ebc4acf8c",
    "dirty": true,
    "id": "benchee",
    "repository_url": "https://github.com/smykla-skalski/benchee",
    "version": "1"
  },
  "reviewer": {
    "id": "afi",
    "label": "afi review",
    "repository_url": "https://github.com/smykla-skalski/afi",
    "tool": {
      "interface": "cli",
      "name": "afi"
    }
  },
  "run_id": "afi/deepseek-v4-pro/20260831T111227Z",
  "runtime": {
    "architecture": "arm64",
    "cache_mode": null,
    "cpus": 14,
    "memory_bytes": 38654705664,
    "os": "Darwin",
    "provider_route": "openrouter",
    "region": null,
    "runner_image": null
  },
  "schema": "benchee-run-1",
  "stamp": "20260831T111227Z",
  "status": {
    "reason": null,
    "state": "completed"
  },
  "target": {
    "base_sha": null,
    "diff_digest": "sha256:eb6648de72c2c54842f91c28e6791a83b671f33293da0f76aeef42c320108ec8",
    "pull_request": 8,
    "repository_url": "https://github.com/smykla-skalski/cairn",
    "reviewed_sha": "9b51f95ef609a219e211e37b082cd2e6913190e0"
  },
  "usage": {
    "reason": null,
    "state": "measured",
    "value": {
      "cached_input_tokens": 13824,
      "input_tokens": 58926,
      "models": null,
      "output_tokens": 1390,
      "reasoning_tokens": 1145,
      "requests": 3,
      "stages": []
    }
  }
}